A particularly challenging problem in AI safety is providing guarantees ...
In their seminal 1990 paper, Wasserman and Kadane establish an upper bou...
Adequate uncertainty representation and quantification have become imper...
Like generic multi-task learning, continual learning has the nature of
m...
As machine learning models continue to achieve impressive performance ac...
Deep neural networks have repeatedly been shown to be non-robust to the
...
Uncertainty quantification and robustness to distribution shifts are
imp...
Given a set of probability measures 𝒫 representing an agent's
knowledge ...
We state concentration and martingale inequalities for the output of the...
We provide optimal variational upper and lower bounds for the augmented
...
We propose a new, more general definition of extended probability measur...
We introduce a new method for updating subjective beliefs based on Jeffr...
In a standard Bayesian setting, there is often ambiguity in prior choice...
In this paper we describe the growth rate of the expected number of
comp...
In this paper we describe the growth rate of the expected number of
comp...
In this paper we relate the geometry of extremal points to properties of...